Skip to content
Orqra
Browse documentation

Getting started

Getting Started

Core setup guides for installing Orqra, connecting model providers, and understanding BYOK responsibility.

What you will complete

After installing a verified build, launch Orqra. Free starts without an account or License.

In this guide

  1. 1
    Open Orqra — After installing a verified build, launch Orqra. Free starts without an account or License.
  2. 2
    Choose your edition — Continue with Free, or activate Personal with the purchase Email and License Key.
  3. 3
    Connect a Provider — Open Models, add your own Provider credentials, choose models, save, and test the connection.
AI drama workflow
Getting StartedAfter installing a verified build, launch Orqra. Free starts without an account or License.

Before you start

  • After installing a verified build, launch Orqra. Free starts without an account or License.
  • Your API Key is stored locally. Never send it to Orqra support or enter it on the Orqra website.
  • Model availability, capabilities, rate limits, and fees are controlled by the Provider. Orqra does not include AI credits.

Complete the task

  1. 1

    Download / Open Orqra

    System requirements

    After installing a verified build, launch Orqra. Free starts without an account or License.

    Expected result

    A verified Orqra build opens on the supported device.

  2. 2

    Free / Account & License

    Choose your edition

    Continue with Free, or activate Personal with the purchase Email and License Key.

    Expected result

    You are using Free, or Personal is activated only if you chose to activate it.

  3. 3

    Models / Service Connections

    Connect a Provider

    Open Models, add your own Provider credentials, choose models, save, and test the connection.

    Expected result

    The Provider connection editor is ready for your own account settings.

  4. 4

    Save / Test Connection / Sync Models

    Test and sync

    Enter the API Key or Provider-specific credentials, then save. Save sensitive changes before testing or syncing models; a saved API Key is not displayed again. Use Test Connection, then Sync Models to refresh the available list. These actions contact the Provider, but they do not run a generation request. Add the models you need to My Models and enable them. Free supports up to 3 enabled models; Personal has no edition-level enabled-model limit.

    Expected result

    The connection is saved, the model list is refreshed, and the models you need are enabled.

  5. 5

    Projects / Add node

    Create a project

    Create a project, add input and processing nodes, connect the flow, and choose the required model.

    Expected result

    A local project contains a connected input-to-processing-to-output workflow.

  6. 6

    Request Preview

    Inspect before running

    Request Preview separates the system prompt, task instruction, resolved inputs, final user input, model, and key parameters.

    Expected result

    Request Preview shows the model, instruction, resolved inputs, and key parameters you intend to send.

  7. 7

    Run / Output node

    Review and run

    Insert reusable templates, inspect the request preview, then run only when the inputs, model, and parameters are correct.

    Expected result

    The run starts only after your explicit action, and the returned output remains attached to the project.

  8. 8

    Local data / Support

    Know what stays local and what leaves the device

    The workspace is local-first and BYOK. Model requests follow the Provider connection you configure.

    Expected result

    You know which data stays local, which Provider receives a request, and where to check a failure.

Checks before you retry

  • Use the endpoint and credential format documented by your Provider or custom gateway.
  • Support can explain Orqra BYOK setup fields, but Orqra does not include AI model API credits and does not resell third-party AI APIs. Provider API keys, billing, rate limits, and model availability remain with your own provider.
  • Creating or editing projects, nodes, and templates does not call a model Provider by itself.